© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 142114
    Prev
    Next
    INDEX
    Explanations

    stone, water, sewer, removing, skeletons

    np_acts-logits-general · gemini-2.5-flash-lite

    allowing or disallowing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    国際
    0.48
    國際
    0.46
    文書
    0.46
    निम्नलिखित
    0.45
    INTERNATIONAL
    0.45
    衛
    0.45
    ﾇ
    0.44
    shooting
    0.43
     విలువ
    0.42
    淔
    0.41
    POSITIVE LOGITS
     vuel
    0.54
     proliferating
    0.47
     abbia
    0.46
     seams
    0.46
     degrad
    0.45
     seguimos
    0.45
     puestos
    0.45
     malef
    0.45
     podamos
    0.44
     preoccup
    0.43
    Activations Density 0.001%

    No Known Activations